Skip to content

Few questions about the radar point clouds #106

Open
@amirbakhtiary23

Description

Hello,
Thank you for your great contribution. I had a few questions about radar point cloud and didn't want to bother you with email.
According to the paper :
The 3+1D radar outputs a point cloud with spatial, Doppler and reflectivity channels for each scan, giving a total of five features for each point: r range, α azimuth, θ elevation, vrel relative radial velocity, and RCS reflectivity. Since most point cloud based object detectors use Cartesian coordinates, we also transform the radar point cloud: p = [x, y, z, vrel, RCS], where p denotes a point, and x, y, z are the three spatial coordinates with x and y axes pointing forward and left respectively w.r.t. the vehicle, see Figure 2. Compensated radial velocity is a signed scalar value denoted by vr, describing the ego-motion compensated (i.e. absolute) radial velocity of the point.
Now the questions, if we consider these x,y,z as coordinates, which one would represent the depth? I suppose its x.
And about the y,z. Since it's mentioned that Z represent elevation, i suppose it means the height, but how is height defined in these cases. I would appreciate if you could help me. Sorry if my questions are basic, I'm a CS major and don't know much about radars.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions